Skip to content
aiqbench

Mistral · model passport

Mistral: Mistral Small 3.1 24B

mistral-small-3-1-24b-instruct-2503
  • Open weights
  • Apache 2.0 licence
  • 24.0B params
  • 128,000 context
  • Released 2025-03-01(from model name)
5/27axes covered
Overall · LMArena
1,303#266 of 396
Best percentile
39.4Coding
Cohort standing
40.2median 45.4

What the data says

Benchmarked on 5 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 13.4 percentile points between its best and worst axis — 39.4 pct on Coding versus 26 pct on Vision Arena.

  • Coding39.4 pct1,361Verify →
  • Instruction following36.9 pct1,293Verify →
  • Hard prompts36.6 pct1,319Verify →
  • Overall33.1 pct1,303Verify →
  • Vision Arena26 pct1,127Verify →
  • WebDev ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • GPQA DiamondNot benchmarked
  • AIME (math)Not benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • LiveBenchNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)Not benchmarked
  • IFBench (Artificial Analysis)Not benchmarked
  • HHEM Hallucination (Vectara)Not benchmarked
  • SWE-bench VerifiedNot benchmarked
  • Terminal-BenchNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

How to run it

Run it yourself

Repositorymistralai/Mistral-Small-3.1-24B-Instruct-2503
Parameters24.0B
ArchitectureMistral3ForConditionalGeneration
LicenceApache 2.0

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

Ollama

We don't sync Ollama tags, so we won't print a command we can't verify — a wrong one would pull the wrong model. Search the Ollama library →

Unsloth fine-tuning recipes are model-specific and we don't derive them here. Unsloth docs →

Use it hosted

API model IDmistralai/mistral-small-3.1-24b-instruct
Context length128,000 tokens
Max output102,400 tokens
Acceptstext, image
Input price$0.35 per 1M tokens
Output price$0.55 per 1M tokens

API parameters this endpoint supports

Frequency penaltyLogit biasLogprobsMax tokensMin-pPresence penaltyRepetition penaltySeedStop sequencesStructured outputsTemperatureTool choiceTool callingTop-kTop logprobsTop-p

Example request

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"mistralai/mistral-small-3.1-24b-instruct","messages":[{"role":"user","content":"Hello"}]}'

View on OpenRouter →

Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.

  • mistral-small-3.1-24b-instruct-2503 stands at 40.2 (raw mean 34.4) — measured on 5 of 27 axes.

    standingtemplateVerify →

  • mistral-small-3.1-24b-instruct-2503 stands at 40.2 versus a cohort median of 45.4 across 144 models released within 180 days — below the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →